|
--- |
|
base_model: google/muril-large-cased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- accuracy |
|
model-index: |
|
- name: Muril-base-finetune-Tamil-qc |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# Muril-base-finetune-Tamil-qc |
|
|
|
This model is a fine-tuned version of [google/muril-large-cased](https://huggingface.co/google/muril-large-cased) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7585 |
|
- Precision: 0.8899 |
|
- Recall: 0.8887 |
|
- Accuracy: 0.8887 |
|
- F1-score: 0.8892 |
|
|
|
## Model description |
|
|
|
More information needed |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 2e-05 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | Accuracy | F1-score | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:--------:|:--------:| |
|
| 0.7778 | 1.0 | 155 | 0.4237 | 0.8573 | 0.8664 | 0.8664 | 0.8605 | |
|
| 0.2769 | 2.0 | 310 | 0.3965 | 0.8789 | 0.8765 | 0.8765 | 0.8769 | |
|
| 0.1657 | 3.0 | 465 | 0.4423 | 0.8889 | 0.8866 | 0.8866 | 0.8870 | |
|
| 0.0975 | 4.0 | 620 | 0.5887 | 0.8824 | 0.8785 | 0.8785 | 0.8798 | |
|
| 0.067 | 5.0 | 775 | 0.6212 | 0.8882 | 0.8846 | 0.8846 | 0.8858 | |
|
| 0.034 | 6.0 | 930 | 0.6018 | 0.8948 | 0.8927 | 0.8927 | 0.8934 | |
|
| 0.0249 | 7.0 | 1085 | 0.7035 | 0.8902 | 0.8887 | 0.8887 | 0.8893 | |
|
| 0.0206 | 8.0 | 1240 | 0.7113 | 0.8936 | 0.8927 | 0.8927 | 0.8931 | |
|
| 0.0122 | 9.0 | 1395 | 0.7400 | 0.8899 | 0.8887 | 0.8887 | 0.8892 | |
|
| 0.0043 | 10.0 | 1550 | 0.7585 | 0.8899 | 0.8887 | 0.8887 | 0.8892 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.3 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
